model_best.pth.tar is corrupt please upload new file

[dexception]

Hi,

Can you provide the new link ... the file at dropbox link is corrupt.

[wondonghyeon]

Could you elaborate what's wrong with the link? It works for me. Thanks!

[dexception]

@wondonghyeon
Is this a regular tar file that can be extracted or we just need to use it as it is ?

[dexception]

Traceback (most recent call last):
File "pred.py", line 118, in
main()
File "pred.py", line 72, in main
model.load_state_dict(torch.load(f)['state_dict'])
File "/usr/local/lib/python3.5/dist-packages/torch/serialization.py", line 387, in load
return _load(f, map_location, pickle_module, **pickle_load_args)
File "/usr/local/lib/python3.5/dist-packages/torch/serialization.py", line 556, in _load
return legacy_load(f)
File "/usr/local/lib/python3.5/dist-packages/torch/serialization.py", line 467, in legacy_load
with closing(tarfile.open(fileobj=f, mode='r:', format=tarfile.PAX_FORMAT)) as tar,
File "/usr/lib/python3.5/tarfile.py", line 1575, in open
return func(name, filemode, fileobj, **kwargs)
File "/usr/lib/python3.5/tarfile.py", line 1605, in taropen
return cls(name, mode, fileobj, **kwargs)
File "/usr/lib/python3.5/tarfile.py", line 1470, in init
self.firstmember = self.next()
File "/usr/lib/python3.5/tarfile.py", line 2279, in next
tarinfo = self.tarinfo.fromtarfile(self)
File "/usr/lib/python3.5/tarfile.py", line 1082, in fromtarfile
buf = tarfile.fileobj.read(BLOCKSIZE)
File "/usr/lib/python3.5/codecs.py", line 321, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 0: invalid start byte

[dexception]

Got it ...
This works with python2 and not python3

[davidGCR]

Could someone give the pytorch versions witch it works?

[damengdameng]

Could someone give the pytorch versions witch it works?

Hi, have you got the answer?

[davidGCR]

@damengdameng, for me it works for pytorch 1.7.1

[damengdameng]

In the case of python3, I just change the

with open(args.model) as f:

to

with open(args.model,'rb') as f:

then the model can be loaded successfully.

[thao-ftech]

In the case of python3, I just change the

with open(args.model) as f:

to

with open(args.model,'rb') as f:

then the model can be loaded successfully.

Confirm this helps for 0.4 torch version.

[sisrfeng]

Hi, could anyone tell us the versions of the requirements?

Pytorch NumPy pandas scikit-learn
Should we use python2 or python3 now (year 2022)?

[yangh-zzf-itcast]

In the case of python3, I just change the

with open(args.model) as f:

to

with open(args.model,'rb') as f:

then the model can be loaded successfully.

hello ，can you provide the model and datasets？thank you very much~